Expandable depth and width adaptive dynamic programming for economic smart generation control of smart grids

TL;DR: Zhang et al. as discussed by the authors proposed lightweight actor-critic generative adversarial networks based on ensemble empirical mode decomposition and evolutionary strategy for increasing the robustness and adaptability of microgrids.

TL;DR: DDAFT-LFC method effectively prevents frequency control loss and reduces total generation cost in island microgrids. It adopts an active fault tolerance strategy and employs a deep meta-deterministic policy gradient (DMDPG) algorithm to adapt to changes in microgrid environment parameters.

TL;DR: DPFOPIDRL algorithm reduces frequency deviations and improves power quality in integrated energy systems by predicting time series signals and controlling prediction signals with fractional-order PID.

TL;DR: In this article , the authors proposed an IoT-based solution for simultaneous load-sharing problem in a hybrid power supply system (HPSS), where the system decides which ON state loads of a household receive power from rooftop solar PV, considering the maximum power available at the rooftop solar plant, and the critical condition arises during the absence of any power sources and/or the lack of both sources.

TL;DR: This review article critically highlights the latest trends in energy storage applications, both cradle and grave and suggests and solutions in mitigating some of these challenges in order to improve the overall performance of these energy systems.

TL;DR: The proposed ADPED algorithm can be adaptive to both day-ahead and intra-day operation under uncertainty and can make full use of historical prediction error distribution to reduce the influence of inaccurate forecast on the system operation.

TL;DR: In this paper, the North American Electric Reliability Council (NERC) replaced A/sub 1/ and A/Sub 2/ with control performance standards CPS1 and CPS2, which assess characteristics of an area's "area control error".

TL;DR: The results from two huge hydropower reservoirs in China show that five artificial intelligence methods can achieve satisfying forecasting results, while the SVM, GPR and ELM methods can produce better performances than ANN and ANFIS in both training and testing phases with respective to four indexes.